Startups · AI

Research Intern, Inference (Winter 2027)

Together AI · San Francisco · On-site

← All jobs
About Together AI

Build what's next on the AI Native Cloud. Full-stack AI platform for inference, fine-tuning, and GPU clusters — powered by cutting-edge research. Backed by General Catalyst, Kleiner Perkins and NEA.

About the role

The Inference Research team is dedicated to building the next generation of efficient, scalable, and reliable serving systems for large foundation models, directly contributing to the mission of advancing open and transparent AI. Our work operates at the critical intersection of cutting-edge model architectures, high-performance systems engineering, and deep hardware optimization. We focus on co-designing software, algorithms, and models to significantly lower the cost and latency of modern AI systems.

What they're looking for

  • Currently pursuing a final year of Bachelor's, Master's, or Ph.D. degree in Computer Science, Electrical Engineering, or a related field
  • Strong knowledge of Machine Learning and Deep Learning fundamentals
  • Experience with deep learning frameworks (PyTorch, JAX, etc.)
  • Strong programming skills in Python
  • Familiarity with Transformer architectures and recent developments in foundation models
More about this role

The Inference Research team is dedicated to building the next generation of efficient, scalable, and reliable serving systems for large foundation models, directly contributing to the mission of advancing open and transparent AI. Our work operates at the critical intersection of cutting-edge model architectures, high-performance systems engineering, and deep hardware optimization. We focus on co-designing software, algorithms, and models to significantly lower the cost and latency of modern AI systems.

As a research intern, you will dive into the complexities of distributed inference, compiler-aware optimization, and novel inference-time computation strategies (such as speculative decoding and phase-aware execution). You will be tasked with co-designing and implementing cross-layer optimizations across models, systems, and hardware, with a focus on areas like KV cache design and large-scale serving architectures.

Projects aim to unlock unprecedented performance and scale for foundation models, enabling faster serving, larger model deployment (e.g., Mixture-of-Experts), and robust, reproducible evaluation under realistic serving workloads.

  • Design and conduct rigorous experiments...

Read the full posting on Together AI's site ↗

Research

Build your edge while you search

Free tools for founders and investors, plus VC Unfiltered, our take on startups, venture and the people who build them.